46 citations · 115 across the 40 of their papers we have counts for
22 papers · 1 filter
Anytime-Feasible Gradient Descent for Constrained Optimization Under Gradient Uncertainty
Sina Sharifi, Jiarui Wang, Mahyar Fazlyab
Constrained optimization is central to many engineering systems in which decisions must satisfy strict safety and operational requirements, especially in real-time settings with li…
Model Predictive Path Integral Control as Preconditioned Gradient Descent
Mahyar Fazlyab, Sina Sharifi, Jiarui Wang
Model Predictive Path Integral (MPPI) control is a widely used sampling-based method for trajectory optimization, yet its convergence properties remain only partially understood. T…
Anytime-Feasible First-Order Optimization via Safe Sequential QCQP
Jiarui Wang, Mahyar Fazlyab
This paper presents the Safe Sequential Quadratically Constrained Quadratic Programming (SS-QCQP) algorithm, a first-order method for smooth inequality-constrained nonconvex optimi…
Sequential QCQP for Bilevel Optimization with Line Search
Sina Sharifi, Erfan Yazdandoost Hamedani, Mahyar Fazlyab
Bilevel optimization involves a hierarchical structure where one problem is nested within another, leading to complex interdependencies between levels. We propose a single-loop, tu…
Perturbed Gradient Descent via Convex Quadratic Approximation for Nonconvex Bilevel Optimization
Nazanin Abolfazli, Sina Sharifi, Mahyar Fazlyab +1
Bilevel optimization is a fundamental tool in hierarchical decision-making and has been widely applied to machine learning tasks such as hyperparameter tuning, meta-learning, and c…
Safe Gradient Flow for Bilevel Optimization
Sina Sharifi, Nazanin Abolfazli, Erfan Yazdandoost Hamedani +1
Bilevel optimization is a key framework in hierarchical decision-making, where one problem is embedded within the constraints of another. In this work, we propose a control-theoret…
Towards Understanding The Semidefinite Relaxations of Truncated Least-Squares in Robust Rotation Search
Liangzu Peng, Mahyar Fazlyab, René Vidal
The rotation search problem aims to find a 3D rotation that best aligns a given number of point pairs. To induce robustness against outliers for rotation search, prior work conside…
On Centralized and Distributed Mirror Descent: Convergence Analysis Using Quadratic Constraints
Youbang Sun, Mahyar Fazlyab, Shahin Shahrampour
Mirror descent (MD) is a powerful first-order optimization technique that subsumes several optimization algorithms including gradient descent (GD). In this work, we develop a semi-…
Learning Lyapunov Functions for Hybrid Systems
Shaoru Chen, Mahyar Fazlyab, Manfred Morari +2
We propose a sampling-based approach to learn Lyapunov functions for a class of discrete-time autonomous hybrid systems that admit a mixed-integer representation. Such systems incl…
Learning Lyapunov Functions for Piecewise Affine Systems with Neural Network Controllers
Shaoru Chen, Mahyar Fazlyab, Manfred Morari +2
We propose a learning-based method for Lyapunov stability analysis of piecewise affine dynamical systems in feedback with piecewise affine neural network controllers. The proposed…
Robust Deep Learning as Optimal Control: Insights and Convergence Guarantees
Jacob H. Seidman, Mahyar Fazlyab, Victor M. Preciado +1
The fragility of deep neural networks to adversarially-chosen inputs has motivated the need to revisit deep learning algorithms. Including adversarial examples during training is a…
Robust Convergence Analysis of Three-Operator Splitting
Han Wang, Mahyar Fazlyab, Shaoru Chen +1
Operator splitting methods solve composite optimization problems by breaking them into smaller sub-problems that can be solved sequentially or in parallel. In this paper, we propos…
A Control-Theoretic Approach to Analysis and Parameter Selection of Douglas-Rachford Splitting
Jacob H. Seidman, Mahyar Fazlyab, Victor M. Preciado +1
Douglas-Rachford splitting and its equivalent dual formulation ADMM are widely used iterative methods in composite optimization problems arising in control and machine learning app…
Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming
Mahyar Fazlyab, Manfred Morari, George J. Pappas
Certifying the safety or robustness of neural networks against input uncertainties and adversarial attacks is an emerging challenge in the area of safe machine learning and control…
A Chebyshev-Accelerated Primal-Dual Method for Distributed Optimization
Jacob H. Seidman, Mahyar Fazlyab, George J. Pappas +1
We consider a distributed optimization problem over a network of agents aiming to minimize a global objective function that is the sum of local convex and composite cost functions.…
Design of First-Order Optimization Algorithms via Sum-of-Squares Programming
Mahyar Fazlyab, Manfred Morari, Victor M. Preciado
In this paper, we propose a framework based on sum-of-squares programming to design iterative first-order optimization algorithms for smooth and strongly convex problems. Our start…
Analysis of Optimization Algorithms via Integral Quadratic Constraints: Nonstrongly Convex Problems
Mahyar Fazlyab, Alejandro Ribeiro, Manfred Morari +1
In this paper, we develop a unified framework able to certify both exponential and subexponential convergence rates for a wide range of iterative first-order optimization algorithm…
Prediction-Correction Interior-Point Method for Time-Varying Convex Optimization
Mahyar Fazlyab, Santiago Paternain, Victor M. Preciado +1
In this paper, we develop an interior-point method for solving a class of convex optimization problems with time-varying objective and constraint functions. Using log-barrier penal…
Self-Triggered Time-Varying Convex Optimization
Mahyar Fazlyab, Cameron Nowzari, George J. Pappas +2
In this paper, we propose a self-triggered algorithm to solve a class of convex optimization problems with time-varying objective functions. It is known that the trajectory of the…
Interior Point Method for Dynamic Constrained Optimization in Continuous Time
Mahyar Fazlyab, Santiago Paternain, Victor M. Preciado +1
This paper considers a class of convex optimization problems where both, the objective function and the constraints, have a continuously varying dependence on time. Our goal is to…
Optimal network design for synchronization of coupled oscillators
Mahyar Fazlyab, Florian Dörfler, Victor M. Preciado
This paper studies the problem of designing networks of nonidentical coupled oscillators in order to achieve a desired level of phase cohesiveness, defined as the maximum asymptoti…
Robust Topology Identification and Control of LTI Networks
Mahyar Fazlyab, Victor M. Preciado
This paper reports a robust scheme for topology identification and control of networks running on linear dynamics. In the proposed method, the unknown network is enforced to asympt…